Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3940 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9289. Min Range: -6.9289
Max Act: 6.9289. Min Act: -0.1700
Data Index: 8308328 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9289. Min Range: -6.9289
Max Act: 6.3039. Min Act: -0.1700
Data Index: 5166853 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9289. Min Range: -6.9289
Max Act: 6.2726. Min Act: -0.1700
Data Index: 3813461 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9289. Min Range: -6.9289
Max Act: 6.0851. Min Act: -0.1700
Data Index: 8212411 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9289. Min Range: -6.9289
Max Act: 5.9289. Min Act: -0.1700
Data Index: 2105797 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9289. Min Range: -6.9289
Max Act: 5.9289. Min Act: -0.1700
Data Index: 1567850 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9289. Min Range: -6.9289
Max Act: 5.8976. Min Act: -0.1700
Data Index: 707682 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9289. Min Range: -6.9289
Max Act: 5.9289. Min Act: -0.1700
Data Index: 8614286 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9289. Min Range: -6.9289
Max Act: 5.8976. Min Act: -0.1700
Data Index: 890788 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9289. Min Range: -6.9289
Max Act: 5.8664. Min Act: -0.1700
Data Index: 7945127 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9289. Min Range: -6.9289
Max Act: 5.8664. Min Act: -0.1700
Data Index: 7339144 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9289. Min Range: -6.9289
Max Act: 5.8664. Min Act: -0.1700
Data Index: 1531609 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9289. Min Range: -6.9289
Max Act: 5.8351. Min Act: -0.1700
Data Index: 446641 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9289. Min Range: -6.9289
Max Act: 5.7726. Min Act: -0.1700
Data Index: 5119170 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9289. Min Range: -6.9289
Max Act: 5.7726. Min Act: -0.1700
Data Index: 8683185 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9289. Min Range: -6.9289
Max Act: 5.7726. Min Act: -0.1700
Data Index: 7635034 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9289. Min Range: -6.9289
Max Act: 5.7414. Min Act: -0.1700
Data Index: 6359914 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9289. Min Range: -6.9289
Max Act: 5.7414. Min Act: -0.1700
Data Index: 7968999 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9289. Min Range: -6.9289
Max Act: 5.7101. Min Act: -0.1700
Data Index: 7699927 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9289. Min Range: -6.9289
Max Act: 5.7101. Min Act: -0.1700
Data Index: 8285884 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19